INDEX

Explanations

quoted strings or documentation comments in code

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<b>

-0.74

-0.70

</b>

-0.69

±

-0.66

ed

-0.64

Хро

-0.64

clé

-0.64

 McCra

-0.64

 Kristina

-0.64

 blue

-0.63

POSITIVE LOGITS

"""

1.88

"""

1.69

."""

1.64

"""

1.36

("""

1.22

 ***!

1.19

""""

1.13

"""

1.09

 MonoBehaviour

1.07

'''

1.07

Activations Density 0.132%

quoted strings or documentation comments in code

No Comments

No Known Activations